Psychological research has long utilized circumplex models to structure emotions, placing similar emotions adjacently and opposing ones diagonally. Although frequently used to interpret deep learning representations, these models are rarely directly incorporated into the representation learning of language models, leaving their geometric validity unexplored. This paper proposes a method to induce circular emotion representations within language model embeddings via contrastive learning on a hypersphere. We show that while this circular alignment offers superior interpretability and robustness against dimensionality reduction, it underperforms compared to conventional designs in high-dimensional settings and fine-grained classification. Our findings elucidate the trade-offs involved in applying psychological circumplex models to deep learning architectures.

翻译：心理学研究长期采用环状模型来构建情绪结构，将相似情绪置于相邻位置，对立情绪置于对角位置。尽管这些模型常被用于解释深度学习表示，却很少直接融入语言模型的表示学习中，其几何有效性亦未得到充分探究。本文提出一种方法，通过超球面上的对比学习在语言模型嵌入中诱导环形情绪表示。研究表明，虽然这种环形对齐在可解释性和对抗降维的鲁棒性方面表现优异，但在高维场景和细粒度分类任务中，其性能逊于传统设计。我们的发现阐明了将心理学环状模型应用于深度学习架构时涉及的权衡关系。